mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
## Summary
- add `approvals_reviewer = "user" | "guardian_subagent"` as the runtime
control for who reviews approval requests
- route Smart Approvals guardian review through core for command
execution, file changes, managed-network approvals, MCP approvals, and
delegated/subagent approval flows
- expose guardian review in app-server with temporary unstable
`item/autoApprovalReview/{started,completed}` notifications carrying
`targetItemId`, `review`, and `action`
- update the TUI so Smart Approvals can be enabled from `/experimental`,
aligned with the matching `/approvals` mode, and surfaced clearly while
reviews are pending or resolved
## Runtime model
This PR does not introduce a new `approval_policy`.
Instead:
- `approval_policy` still controls when approval is needed
- `approvals_reviewer` controls who reviewable approval requests are
routed to:
- `user`
- `guardian_subagent`
`guardian_subagent` is a carefully prompted reviewer subagent that
gathers relevant context and applies a risk-based decision framework
before approving or denying the request.
The `smart_approvals` feature flag is a rollout/UI gate. Core runtime
behavior keys off `approvals_reviewer`.
When Smart Approvals is enabled from the TUI, it also switches the
current `/approvals` settings to the matching Smart Approvals mode so
users immediately see guardian review in the active thread:
- `approval_policy = on-request`
- `approvals_reviewer = guardian_subagent`
- `sandbox_mode = workspace-write`
Users can still change `/approvals` afterward.
Config-load behavior stays intentionally narrow:
- plain `smart_approvals = true` in `config.toml` remains just the
rollout/UI gate and does not auto-set `approvals_reviewer`
- the deprecated `guardian_approval = true` alias migration does
backfill `approvals_reviewer = "guardian_subagent"` in the same scope
when that reviewer is not already configured there, so old configs
preserve their original guardian-enabled behavior
ARC remains a separate safety check. For MCP tool approvals, ARC
escalations now flow into the configured reviewer instead of always
bypassing guardian and forcing manual review.
## Config stability
The runtime reviewer override is stable, but the config-backed
app-server protocol shape is still settling.
- `thread/start`, `thread/resume`, and `turn/start` keep stable
`approvalsReviewer` overrides
- the config-backed `approvals_reviewer` exposure returned via
`config/read` (including profile-level config) is now marked
`[UNSTABLE]` / experimental in the app-server protocol until we are more
confident in that config surface
## App-server surface
This PR intentionally keeps the guardian app-server shape narrow and
temporary.
It adds generic unstable lifecycle notifications:
- `item/autoApprovalReview/started`
- `item/autoApprovalReview/completed`
with payloads of the form:
- `{ threadId, turnId, targetItemId, review, action? }`
`review` is currently:
- `{ status, riskScore?, riskLevel?, rationale? }`
- where `status` is one of `inProgress`, `approved`, `denied`, or
`aborted`
`action` carries the guardian action summary payload from core when
available. This lets clients render temporary standalone pending-review
UI, including parallel reviews, even when the underlying tool item has
not been emitted yet.
These notifications are explicitly documented as `[UNSTABLE]` and
expected to change soon.
This PR does **not** persist guardian review state onto `thread/read`
tool items. The intended follow-up is to attach guardian review state to
the reviewed tool item lifecycle instead, which would improve
consistency with manual approvals and allow thread history / reconnect
flows to replay guardian review state directly.
## TUI behavior
- `/experimental` exposes the rollout gate as `Smart Approvals`
- enabling it in the TUI enables the feature and switches the current
session to the matching Smart Approvals `/approvals` mode
- disabling it in the TUI clears the persisted `approvals_reviewer`
override when appropriate and returns the session to default manual
review when the effective reviewer changes
- `/approvals` still exposes the reviewer choice directly
- the TUI renders:
- pending guardian review state in the live status footer, including
parallel review aggregation
- resolved approval/denial state in history
## Scope notes
This PR includes the supporting core/runtime work needed to make Smart
Approvals usable end-to-end:
- shell / unified-exec / apply_patch / managed-network / MCP guardian
review
- delegated/subagent approval routing into guardian review
- guardian review risk metadata and action summaries for app-server/TUI
- config/profile/TUI handling for `smart_approvals`, `guardian_approval`
alias migration, and `approvals_reviewer`
- a small internal cleanup of delegated approval forwarding to dedupe
fallback paths and simplify guardian-vs-parent approval waiting (no
intended behavior change)
Out of scope for this PR:
- redesigning the existing manual approval protocol shapes
- persisting guardian review state onto app-server `ThreadItem`s
- delegated MCP elicitation auto-review (the current delegated MCP
guardian shim only covers the legacy `RequestUserInput` path)
---------
Co-authored-by: Codex <noreply@openai.com>
80 lines
3.5 KiB
Rust
80 lines
3.5 KiB
Rust
use codex_utils_absolute_path::AbsolutePathBuf;
|
|
use schemars::JsonSchema;
|
|
use serde::Deserialize;
|
|
use serde::Serialize;
|
|
|
|
use crate::config::ToolsToml;
|
|
use crate::config::types::ApprovalsReviewer;
|
|
use crate::config::types::Personality;
|
|
use crate::config::types::WindowsToml;
|
|
use crate::protocol::AskForApproval;
|
|
use codex_protocol::config_types::ReasoningSummary;
|
|
use codex_protocol::config_types::SandboxMode;
|
|
use codex_protocol::config_types::ServiceTier;
|
|
use codex_protocol::config_types::Verbosity;
|
|
use codex_protocol::config_types::WebSearchMode;
|
|
use codex_protocol::openai_models::ReasoningEffort;
|
|
|
|
/// Collection of common configuration options that a user can define as a unit
|
|
/// in `config.toml`.
|
|
#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize, JsonSchema)]
|
|
#[schemars(deny_unknown_fields)]
|
|
pub struct ConfigProfile {
|
|
pub model: Option<String>,
|
|
pub service_tier: Option<ServiceTier>,
|
|
/// The key in the `model_providers` map identifying the
|
|
/// [`ModelProviderInfo`] to use.
|
|
pub model_provider: Option<String>,
|
|
pub approval_policy: Option<AskForApproval>,
|
|
pub approvals_reviewer: Option<ApprovalsReviewer>,
|
|
pub sandbox_mode: Option<SandboxMode>,
|
|
pub model_reasoning_effort: Option<ReasoningEffort>,
|
|
pub plan_mode_reasoning_effort: Option<ReasoningEffort>,
|
|
pub model_reasoning_summary: Option<ReasoningSummary>,
|
|
pub model_verbosity: Option<Verbosity>,
|
|
/// Optional path to a JSON model catalog (applied on startup only).
|
|
pub model_catalog_json: Option<AbsolutePathBuf>,
|
|
pub personality: Option<Personality>,
|
|
pub chatgpt_base_url: Option<String>,
|
|
/// Optional path to a file containing model instructions.
|
|
pub model_instructions_file: Option<AbsolutePathBuf>,
|
|
pub js_repl_node_path: Option<AbsolutePathBuf>,
|
|
/// Ordered list of directories to search for Node modules in `js_repl`.
|
|
pub js_repl_node_module_dirs: Option<Vec<AbsolutePathBuf>>,
|
|
/// Optional absolute path to patched zsh used by zsh-exec-bridge-backed shell execution.
|
|
pub zsh_path: Option<AbsolutePathBuf>,
|
|
/// Deprecated: ignored. Use `model_instructions_file`.
|
|
#[schemars(skip)]
|
|
pub experimental_instructions_file: Option<AbsolutePathBuf>,
|
|
pub experimental_compact_prompt_file: Option<AbsolutePathBuf>,
|
|
pub include_apply_patch_tool: Option<bool>,
|
|
pub experimental_use_unified_exec_tool: Option<bool>,
|
|
pub experimental_use_freeform_apply_patch: Option<bool>,
|
|
pub tools_view_image: Option<bool>,
|
|
pub tools: Option<ToolsToml>,
|
|
pub web_search: Option<WebSearchMode>,
|
|
pub analytics: Option<crate::config::types::AnalyticsConfigToml>,
|
|
#[serde(default)]
|
|
pub windows: Option<WindowsToml>,
|
|
/// Optional feature toggles scoped to this profile.
|
|
#[serde(default)]
|
|
// Injects known feature keys into the schema and forbids unknown keys.
|
|
#[schemars(schema_with = "crate::config::schema::features_schema")]
|
|
pub features: Option<crate::features::FeaturesToml>,
|
|
pub oss_provider: Option<String>,
|
|
}
|
|
|
|
impl From<ConfigProfile> for codex_app_server_protocol::Profile {
|
|
fn from(config_profile: ConfigProfile) -> Self {
|
|
Self {
|
|
model: config_profile.model,
|
|
model_provider: config_profile.model_provider,
|
|
approval_policy: config_profile.approval_policy,
|
|
model_reasoning_effort: config_profile.model_reasoning_effort,
|
|
model_reasoning_summary: config_profile.model_reasoning_summary,
|
|
model_verbosity: config_profile.model_verbosity,
|
|
chatgpt_base_url: config_profile.chatgpt_base_url,
|
|
}
|
|
}
|
|
}
|